Hidekata Hontani

Robust nonrigid ICP using outlier-sparsity regularization

We show how to incorporate a statistical shape model into the nonrigid ICP framework, and propose a robust nonrigid ICP algorithm. In the nonrigid ICP framework, a template surface is represented by a set of points, and the shape of the template is parametrized by a transformation matrix per one template point. In the proposed method, the statistics of the matrices are estimated based on a set of training surfaces, and the statistical shape model is incorporated into the nonrigid ICP framework by modifying the representation of the stiffness of the template. The statistical shape model and a noise model make it possible to discriminate outliers from inliers in given targets. Our proposed method detects the outliers, which are not represented by the models appropriately, based on their sparseness. The detected outliers are automatically excluded from the target to be registered, and the template is deformed to fit the inliers only. As the result, the accuracy of the registration is improved. The performance of the proposed method is evaluated qualitatively and quantitatively using synthetic data and clinical CT images.

3D fundus pattern reconstruction and display from multiple fundus images

This paper proposes a method to reconstruct and display 3D fundus (inner bottom of eye-ball) pattern from a set of multiple partial images of fundus. They were taken from several different view angles by shifting fundus camera. Since they are distorted by eye lens, a simple stereo technique does not work for the 3D reconstruction from any pair of images. Moreover, every fundus images distortions differ from each other. In this method, we utilize the fact that a fundus has a spherical shape and that the image of sphere by the eye lens results in a quadratic surface. First, we determine each cameras viewing position and pose relative to the eye-ball and the shape of the quadratic surface by matching feature points in every fundus image on the quadratic image surface. Then, we identify the eye lens parameters so that the quadratic surface should be originated from a spherical fundus surface. As the final result, we obtain a wide area 3D fundus pattern reconstructed from the set of fundus images.

A study on graphical model structure for representing statistical shape model of point distribution model

In this article, the authors demonstrate that you can improve the performance of the registration of a point distribution model (PDM) by accurately estimating the structure of an undirected graphical model that represents the statistical shape model (SSM) of a target surface. Many existing methods for constructing SSMs determine the structure of the graphical model without analyzing the conditional dependencies among the points in PDM, though an edge in the PDM should link two nodes if and only if they are conditionally dependent. In this study, the authors employed four popular methods for estimating the structure of graphical model and obtained four different SSMs from an identical set of training surfaces. The registration performances of the SSMs were experimentally compared, and the results showed that the graphical lasso, which could estimate more accurate structure of the graphical model by avoiding the overfitting to the training data, outperformed the other methods.

A System of Networked Car-Mounted Sensors for Measuring Road Surfaces

In this article, we propose a system of networked car-mounted sensors that measures road surfaces. The system consists of cars each of which carries a GPS, an accelerometer, a torque meter, and a rotating meter of a wheel. The proposed system estimates angles of inclination of road surfaces and their friction coefficients based on measurements obtained by the sensors. Each car obtains the measurements at each location while moving, and uploads those measurements to a server. The server estimates the angles and the friction coefficients based on the uploaded measurements. We model the dynamics of moving cars, and derive constraint conditions that should be satisfied by the measurements. We compute the maximum likelihood estimates of the coefficients with the measurements under the constraint conditions. The ML solution, however, can contain indeterminacies and have two degrees of freedom. Hence, we need two more constraints for removing the indeterminacies. For this purpose, one set of car-mounted sensors that is calibrated in advance is incorporated into the car-mounted sensor network. We call the calibrated sensor a reference sensor. If the reference sensor removes the indeterminacies we can obtain unique set of ML estimates, but the set of estimates is perturbed by the measurement noise. Defining the distance between two sensors based on a measurement graph, in this article, we analyze the relationship between the variance of the estimates and the distance between a sensor and the reference sensor

Point-based non-rigid surface registration with accuracy estimation

This article presents a new method for non-rigid surface registration between a surface model and a surface of an internal organ in a given 3D medical image. The surface is represented with a set of feature points, of which locations are represented by a graphical model. For constructing the representation, a set of corresponding points is distributed on each of training surfaces based on an entropy-based particle system. From these corresponding points, we estimate probability densities of the location of each feature point, the conditional probability distribution of the local image pattern around each feature point, and the probability distributions of relative positions between two neighboring feature points. When a new image is given, these densities are used for estimating the location of each feature point by means of a non-parametric belief propagation. The proposed method can estimate not only the locations of the feature points but also their conditional marginal distributions in a given image. Some experimental results obtained from real X-CT images are presented to show its performance.

Quantitative evaluation of myocardial function by a volume-normalized map generated from relative blood flow.

Our study aimed to quantitatively evaluate blood flow in the left ventricle (LV) of apical hypertrophic cardiomyopathy (APH) by combining wall thickness obtained from cardiac magnetic resonance imaging (MRI) and myocardial perfusion from single-photon emission computed tomography (SPECT). In this study, we considered paired MRI and myocardial perfusion SPECT from ten patients with APH and ten normals. Myocardial walls were detected using a level set method, and blood flow per unit myocardial volume was calculated using 3D surface-based registration between the MRI and SPECT images. We defined relative blood flow based on the maximum in the whole myocardial region. Accuracies of wall detection and registration were around 2.50 mm and 2.95 mm, respectively. We finally created a bulls-eye map to evaluate wall thickness, blood flow (cardiac perfusion) and blood flow per unit myocardial volume. In patients with APH, their wall thicknesses were over 10 mm. Decreased blood flow per unit myocardial volume was detected in the cardiac apex by calculation using wall thickness from MRI and blood flow from SPECT. The relative unit blood flow of the APH group was 1/7 times that of the normals in the apex. This normalization by myocardial volume distinguishes cases of APH whose SPECT images resemble the distributions of normal cases.

Vehicle positioning method with car-to-car communications in consideration of communication delay

In this article, the authors propose a car positioning method that can estimate the positions of cars even in areas where the GPS is not available. For the estimation, each car measures the relative distance to a car running in front, communicates the measurements with other cars, and uses the received measurements for estimating its position. In order to estimate the position even if the measurements are received with time-delay, the authors employed the time-delay tolerant Kalman filtering. For sharing the measurements, it is assumed that a car-to-car communication system is used. Then, the measurements sent from farther cars are received with larger time-delay. It follows that the accuracy of the estimates of farther cars become worse. Hence, the proposed method manages only the states of nearby cars to reduce computing effort. The authors simulated the proposed filtering method and found that the proposed method estimates the positions of nearby cars as accurate as the distributed Kalman filtering.

Improvement of Vehicle Positioning Using Car-to-Car Communications in Consideration of Communication Delay

In this article, we propose a vehicle positioning method that can estimate positions of cars even in areas where the GPS is not available. For the estimation, each car measures the relative distance to a car running in front, communicates the measurements with other cars, and uses the received measurements for estimating its position. In order to estimate the position even if the measurements are received with time-delay, we employed the time-delay tolerant Kalman filtering. For sharing the measurements, it is assumed that a car-to-car communication system is used. Then, the measurements sent from farther cars are received with larger time-delay. It follows that the accuracy of the estimates of farther cars become worse. Hence, the proposed method manages only the states of nearby cars to reduce computing effort. The authors simulated the proposed filtering method and found that the proposed method estimates the positions of nearby cars as accurate as the distributed Kalman filtering.

Local Estimation of High Velocity Optical Flow with Correlation Image Sensor

In this article, the authors address a problem of the estimation of high velocity optical flow. When images are captured by conventional image sensors, the problem of the optical flow estimation is ill-posed if only the temporal constancy of the image brightness is the valid assumption. When given images are captured by the correlation image sensors, though, you can make the problem of the optical flow estimation well-posed under some condition and can locally estimate the unique optical flow at each pixel in each single frame. The condition though would not be satisfied when the flow velocity is high. In this article, we propose a method that can estimate the normal component of high velocity optical flow using only the local image values in each single frame. The equation used for estimating the normal velocity is theoretically derived and the condition the equation holds is also revealed.

Simultaneous Visual Data Completion and Denoising Based on Tensor Rank and Total Variation Minimization and Its Primal-Dual Splitting Algorithm

Tensor completion has attracted attention because of its promising ability and generality. However, there are few studies on noisy scenarios which directly solve an optimization problem consisting of a noise inequality constraint. In this paper, we propose a new tensor completion and denoising model including tensor total variation and tensor nuclear norm minimization with a range of values and noise inequalities. Furthermore, we developed its solution algorithm based on a primal-dual splitting method, which is computationally efficient as compared to tensor decomposition based non-convex optimization. Lastly, extensive experiments demonstrated the advantages of the proposed method for visual data retrieval such as for color images, movies, and 3D-volumetric data.